26 accepted papers
Recent approaches for few-shot 3D point cloud semantic segmentation typically require a two-stage learning process, i.e., a pre-training stage followed by a few-shot training stage. While effective, these methods face overreliance on pre-training, which hinders model flexibility and adaptability. So
Robotic systems demand accurate and comprehensive 3D environment perception, requiring simultaneous capture of photo-realistic appearance (optical), precise layout shape (geometric), and open-vocabulary scene understanding (semantic). Existing methods typically achieve only partial fulfillment of th…
Planar structures, ubiquitous in man-made indoor environments, enable compact and accurate scene abstraction for various downstream tasks. Recent methods distill planar features into learning-based MVS geometries to obtain coherent 3D plane estimation from multi-view inputs. However, the lack of exp…
Outdoor loop closure detection is essential for mitigating accumulated drift in SLAM and generating a global consistent map. Semantic graph matching methods utilize object-level topology for distinctive scene representation but rely on environments with rich and distinguishable objects. Moreover, ac…
Scalable robot learning is hindered by the high cost of acquiring diverse, high-quality embodied data. Existing data generation approaches partially mitigate this issue but typically depend on hard-to-access hardware and labor-intensive manual effort, with limited generalization to diverse scene con
Visual navigation is essential for robotics and embodied AI. However, existing foundation models, particularly those with transformer decoders, suffer from high computational overhead and lack interpretability, limiting their deployment on edge devices. To address this, we propose DynaNav, a Dynamic…
Unsupervised domain adaptation (UDA) is a machine learning approach designed to minimize reliance on labeled data by aligning features between a labeled source domain and an unlabeled target domain, thereby reducing feature discrepancies, which is efficient for multivariate time series (MTS) predict…
Visual reinforcement learning has shown promise in various real-world applications. However, deploying policies in complex real-world environments with visual perturbations remains a significant challenge. We notice that humans tend to filter information at the object level prior to decision-making,…
Implicit reconstruction of ESDF (Euclidean Signed Distance Field) involves training a neural network to regress the signed distance from any point to the nearest obstacle, which has the advantages of lightweight storage and continuous querying. However, existing algorithms usually rely on conflictin
Aligning Large Language Models (LLMs) with human feedback is crucial for their development. Existing preference optimization methods such as DPO and KTO, while improved based on Reinforcement Learning from Human Feedback (RLHF), are inherently derived from PPO, requiring a reference model that adds…
Recently, the metric-based prototypical methods achieves promising performance in few-shot learning (FSL) for hyperspectral image (HSI) classification. However, the existing models are easily affected by the noisy pixels of different categories around the center pixel of the patch, and tend to focus…
Despite LLMs’ excellent code creation capabilities, multilingual code generation remains extremely challenging. To address this, we intent to improve the multi-programming-lingual (MultiPL) performance of the base LLMs while retaining the most popular ones using restricted computational resources. W
Open-vocabulary scene understanding is critical for robotics, yet existing 3D Gaussian Splatting (3DGS) methods rely on compressed feature embeddings, compromising semantic fidelity and fine-grained interpretation. Although utilizing uncompressed high-dimensional features offers a potential solution
Multi-agent distributed collaborative mapping provides comprehensive and efficient representations for robots. However, existing approaches lack instance-level awareness and semantic understanding of environments, limiting their effectiveness for downstream applications. To address this issue, we pr
In recent years, there has been a surge of interest in open-vocabulary 3D scene reconstruction facilitated by visual language models (VLMs), which showcase remarkable capabilities in open-set retrieval tasks. Although the semantic ambiguity of existing point-wise feature maps is alleviated by open-v
It has been observed that even a small amount of noise introduced into the dataset can significantly degrade the performance of KAN. In this brief note, we aim to quantitatively evaluate the performance when noise is added to the dataset. We propose an oversampling technique combined with denoising…
Recent 6D pose estimation methods demonstrate notable performance but still face some practical limitations. For instance, many of them rely heavily on sensor depth, which may fail with challenging surface conditions, such as transparent or highly reflective materials. In the meantime, RGB-based sol…
Multimodal Large Language Models (MLLMs) are commonly derived by extending pre-trained Large Language Models (LLMs) with visual capabilities. In this work, we investigate how MLLMs process visual inputs by analyzing their attention mechanisms. We reveal a surprising sparsity phenomenon: only a small…
In field environments, numerous robots necessitate manual intervention for restoration of functionality post a turnover, resulting in diminished operational efficiency. This study presents an innovative design solution for a reversible omnidirectional mobile robot denoted as CuRobot, featuring a cub
"In the field of instruction-following large vision-language models (LVLMs), the efficient deployment of these models faces challenges, notably due to the high memory demands of their key-value (KV) caches. Conventional cache management strategies for LLMs focus on cache eviction, which often fails…
Active learning (AL) aims to reduce labeling costs by selecting the most valuable samples to annotate from a set of unlabeled data. However, recognizing these samples is particularly challenging in multi-label text classification tasks due to the high dimensionality but sparseness of label spaces. E…
Recently the dense Simultaneous Localization and Mapping (SLAM) based on neural implicit representation has shown impressive progress in hole filling and high-fidelity mapping. Nevertheless, existing methods either heavily rely on known scene bounds or suffer inconsistent reconstruction due to drift…
Environment representations endowed with sophisticated semantics are pivotal for facilitating seamless interaction between robots and humans, enabling them to effectively carry out various tasks. Open-vocabulary representation, powered by Visual-Language models (VLMs), possesses inherent advantages,
As one of the most popular machine learning tools in the field of unsupervised learning, clustering has been widely used in various practical applications. While numerous methods have been proposed for clustering, a commonly encountered issue is that the existing clustering methods rely heavily on l…
This paper presents an effective few-shot point cloud semantic segmentation approach for real-world applications. Existing few-shot segmentation methods on point cloud heavily rely on the fully-supervised pretrain with large annotated datasets, which causes the learned feature extraction bias to tho…